© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15084
    Prev
    Next
    INDEX
    Explanations

    words related to legal arguments, courts, and decisions

    oai_token-act-pair · gemini-2.0-flash

    legal/academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.90
    Enllaços
    -0.65
    ьаж
    -0.59
     transférez
    -0.59
     мәкал
    -0.57
     OFDb
    -0.56
     JAXBElement
    -0.56
    witzerland
    -0.55
    zzleHttp
    -0.55
     חיצוניים
    -0.54
    POSITIVE LOGITS
    ArgsConstructor
    0.58
     biograf
    0.58
    Busch
    0.50
     '\\;'
    0.50
    endregion
    0.49
    =@"
    0.49
    ⬇️
    0.49
    Ans
    0.48
    TagHelper
    0.47
    Traditional
    0.47
    Activations Density 27.361%

    No Known Activations